Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition

  title={Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition},
  author={J. Zang and L. Wang and Z. Liu and Q. Zhang and Zhenxing Niu and Gang Hua and Nanning Zheng},
  • J. Zang, L. Wang, +4 authors Nanning Zheng
  • Published in AIAI 2018
  • Computer Science
  • Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of temporal information into CNNs are still being actively explored in the recent literature. Motivated by the popular recurrent attention models in the research area of natural language processing, we propose the Attention-based Temporal Weighted CNN (ATW), which… CONTINUE READING
    30 Citations
    Action Recognition by an Attention-Aware Temporal Weighted Convolutional Neural Network
    • 15
    • PDF
    Convolutional Networks With Channel and STIPs Attention Model for Action Recognition in Videos
    Convolutional Neural Networks with Generalized Attentional Pooling for Action Recognition
    • 2
    Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network
    • 6
    • PDF
    An Improved Attention-Based Spatiotemporal-Stream Model for Action Recognition in Videos
    Joint spatial-temporal attention for action recognition
    • 7
    Dual Stream Spatio-Temporal Motion Fusion With Self-Attention For Action Recognition
    • 1
    • Highly Influenced
    Deep Spatial–Temporal Model Based Cross-Scene Action Recognition Using Commodity WiFi
    • 1


    Convolutional Two-Stream Network Fusion for Video Action Recognition
    • 1,402
    • PDF
    Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks
    • 353
    • PDF
    Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
    • 1,539
    • Highly Influential
    • PDF
    Two-Stream Convolutional Networks for Action Recognition in Videos
    • 4,092
    • Highly Influential
    • PDF
    Beyond short snippets: Deep networks for video classification
    • 1,562
    • PDF
    Describing Videos by Exploiting Temporal Structure
    • 731
    • PDF
    Long-Term Temporal Convolutions for Action Recognition
    • 526
    • PDF
    3D Convolutional Neural Networks for Human Action Recognition
    • 3,271
    • Highly Influential
    • PDF
    Large-Scale Video Classification with Convolutional Neural Networks
    • 4,178
    • PDF
    Action recognition with trajectory-pooled deep-convolutional descriptors
    • L. Wang, Yu Qiao, X. Tang
    • Computer Science
    • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2015
    • 863
    • PDF